Neuro-Symbolic AI for Context-Aware Automation in Smart Factories

  • Authors

    • Rahul Mehta Senior Software Engineer, Wipro Ltd., India. Author
    • Priya Kapoor Business Analyst, Accenture, India. Author

    DOI:

    https://doi.org/10.67228/3142788X/IJMLPA-2021PI9B8L

    Published 01-03-2021

  • Neuro-Symbolic AI, Context-Aware Automation, Smart Factories, Industry 4.0, Hybrid AI Systems, Manufacturing Intelligence, Symbolic Reasoning, Neural Networks, Industrial Automation

    Issue

    Vol. 4 No. 1 (2021)

    Section

    Articles

    How to Cite

    [1]
    R. Mehta and P. Kapoor, “Neuro-Symbolic AI for Context-Aware Automation in Smart Factories”, IJMLPA, vol. 4, no. 1, pp. 01–12, Jan. 2021, doi: 10.67228/3142788X/IJMLPA-2021PI9B8L.

  • Abstract

    Smart factories under Industry 4.0 demand highly adaptive and context-aware automation systems to optimize manufacturing processes, enhance operational efficiency, and ensure safety. Traditional AI approaches, either symbolic or neural, face limitations when applied in isolation—symbolic methods lack adaptability, while neural networks struggle with explainability and reasoning. This paper proposes a neuro-symbolic AI framework that synergistically combines neural perception and learning with symbolic reasoning to enable robust, context-aware automation in smart factories. The framework incorporates real-time environmental, operational, and human context data to enhance decision-making processes. Experimental evaluations demonstrate the proposed system's superior performance in accuracy, adaptability, and interpretability compared to conventional AI methods. The findings underscore neuro-symbolic AI's potential as a transformative approach for next-generation smart factory automation.

  • References

    [1] Garcez, A. S., Lamb, L. C., & Gabbay, D. M. (2019). Neurosymbolic AI: The 3rd Wave. Springer.

    [2] Besold, T. R., Garcez, A. S., Bader, S., Bowman, H., Domingos, P., Hitzler, P., ... & Valiant, L. (2017). Neural-symbolic learning and reasoning: A survey and interpretation. arXiv preprint arXiv:1711.03902.

    [3] Lee, J., Bagheri, B., & Kao, H. A. (2015). A cyber-physical systems architecture for Industry 4.0-based manufacturing systems. Manufacturing Letters, 3, 18-23.

    [4] Chen, C., Xu, C., Lu, C., & Chen, C. H. (2021). Neuro-symbolic learning for intelligent manufacturing: A review. Journal of Manufacturing Systems, 59, 182-195.

    [5] Russell, S., & Norvig, P. (2021). Artificial Intelligence: A Modern Approach (4th ed.). Pearson.

    [6] Xu, L. D., Xu, E. L., & Li, L. (2018). Industry 4.0: state of the art and future trends. International Journal of Production Research, 56(8), 2941-2962.

    [7] Taatgen, N. A., & Anderson, J. R. (2016). Constraints in cognitive architectures. Psychological Review, 123(4), 499-523.

    [8] Zadeh, L. A. (2017). From computing with numbers to computing with words—From manipulation of measurements to manipulation of perceptions. International Journal of Applied Mathematics and Computer Science, 7(3), 307-324.

    [9] He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 770-778).

    [10] Besold, T. R., Garcez, A. S., & Lamb, L. C. (2020). Neuro-symbolic AI: Trends and future directions. In Explainable AI: Interpreting, Explaining and Visualizing Deep Learning (pp. 123-131). Springer.

    [11] Bader, S., & Hitzler, P. (2019). Dimensions of neural-symbolic integration—A structured survey. arXiv preprint arXiv:1905.06088.

    [12] Qin, J., Liu, Y., & Grosvenor, R. (2016). A framework of energy consumption modeling for additive manufacturing based on cyber-physical systems. Procedia CIRP, 52, 46-51.

    [13] Jin, Y., & Li, W. (2020). Hybrid neural-symbolic learning and reasoning for complex industrial processes. Engineering Applications of Artificial Intelligence, 90, 103494.

    [14] LeCun, Y., Bengio, Y., & Hinton, G. (2015). Deep learning. Nature, 521(7553), 436-444.

  • Downloads